Title :
Face recognition using PCA based immune networks with single training sample per person
Author_Institution :
Dept. of Mech. Eng., Tatung Univ., Taipei, Taiwan
Abstract :
Numerous methods could deal well with frontal view face recognition if there were sufficient number of representative training samples. Nevertheless, few of them work well when only single training sample per person is available. In this paper, a face recognition method using artificial immune networks based on Principal Component Analysis (PCA) is proposed to solve the one training sample problem. The performance of the present method was evaluated employing the ORL face database. The results show that this method gains higher recognition rate in contrast with most of the developed methods.
Keywords :
artificial immune systems; face recognition; principal component analysis; visual databases; ORL face database; PCA based immune networks; artificial immune networks; face recognition; principal component analysis; single training sample per person; Covariance matrix; Databases; Face; Face recognition; Immune system; Principal component analysis; Training; Artificial immune networks; Face recognition; ORL; One training sample problem; Principle component analysis;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2011 International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-1-4577-0305-8
DOI :
10.1109/ICMLC.2011.6017003